© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21471
    Prev
    Next
    INDEX
    Explanations

    bias and offset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨæŀIJä¸İ
    -0.06
    çĿ¿
    -0.06
    пÑĭ
    -0.05
    æľīçĶ¨çļĦ
    -0.05
    åĩ½
    -0.05
    æĹłçijķ
    -0.05
     Expo
    -0.05
    adin
    -0.05
    oló
    -0.05
     dusty
    -0.05
    POSITIVE LOGITS
     neg
    0.06
    建åĨĽ
    0.06
     Mig
    0.05
    ügt
    0.05
    cept
    0.05
    sweet
    0.05
    端起
    0.05
     gag
    0.05
    ffen
    0.05
     misrepresented
    0.05
    Activations Density 0.002%

    No Known Activations